# Feature Alignment and Uniformity for Test Time Adaptation

arXiv: https://arxiv.org/abs/2303.10902 · HTML: https://mlsanity.com/paper/2303.10902/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- Builds on 56 of its 82 references that are in the map.
- First posted on arXiv 20 Mar 2023.

## Builds on (most cited first, 30 of 56)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [In Search of Lost Domain Generalization](https://mlsanity.com/paper/2007.01434/) (2020)
- [Deeper, Broader and Artier Domain Generalization](https://mlsanity.com/paper/1710.03077/) (2017)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Learning to Generalize: Meta-Learning for Domain Generalization](https://mlsanity.com/paper/1710.03463/) (2017)
- [The Medical Segmentation Decathlon](https://mlsanity.com/paper/2106.05735/) (2021)
- [Deep Domain Confusion: Maximizing for Domain Invariance](https://mlsanity.com/paper/1412.3474/) (2014)
- [Domain Generalization with MixStyle](https://mlsanity.com/paper/2104.02008/) (2021)

## Built on by (most cited first, 30 of 42)

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Video Understanding with Large Language Models: A Survey](https://mlsanity.com/paper/2312.17432/) (2023)
- [In Search of Lost Online Test-time Adaptation: A Survey](https://mlsanity.com/paper/2310.20199/) (2023)
- [Each Test Image Deserves A Specific Prompt: Continual Test-Time Adaptation for 2D Medical Image Segmentation](https://mlsanity.com/paper/2311.18363/) (2023)
- [Historical Test-time Prompt Tuning for Vision Foundation Models](https://mlsanity.com/paper/2410.20346/) (2024)
- [BoostAdapter: Improving Vision-Language Test-Time Adaptation via Regional Bootstrapping](https://mlsanity.com/paper/2410.15430/) (2024)
- [Efficient Test-Time Prompt Tuning for Vision-Language Models](https://mlsanity.com/paper/2408.05775/) (2024)
- [Reshaping the Online Data Buffering and Organizing Mechanism for Continual Test-Time Adaptation](https://mlsanity.com/paper/2407.09367/) (2024)
- [Generalizable Person Re-identification via Balancing Alignment and Uniformity](https://mlsanity.com/paper/2411.11471/) (2024)
- [Decoupled Prototype Learning for Reliable Test-Time Adaptation](https://mlsanity.com/paper/2401.08703/) (2024)
- [A Layer Selection Approach to Test Time Adaptation](https://mlsanity.com/paper/2404.03784/) (2024)
- [MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection](https://mlsanity.com/paper/2406.14878/) (2024)
- [Low Saturation Confidence Distribution-based Test-Time Adaptation for Cross-Domain Remote Sensing Image Classification](https://mlsanity.com/paper/2408.16265/) (2024)
- [Enhancing Test Time Adaptation with Few-shot Guidance](https://mlsanity.com/paper/2409.01341/) (2024)
- [Feature Augmentation based Test-Time Adaptation](https://mlsanity.com/paper/2410.14178/) (2024)
- [Is Less More? Exploring Token Condensation as Training-free Test-time Adaptation](https://mlsanity.com/paper/2410.14729/) (2024)
- [Towards Understanding Extrapolation: a Causal Lens](https://mlsanity.com/paper/2501.09163/) (2025)
- [Adapting In-Domain Few-Shot Segmentation to New Domains without Source Domain Retraining](https://mlsanity.com/paper/2504.21414/) (2025)
- [Test-time Correlation Alignment](https://mlsanity.com/paper/2505.00533/) (2025)
- [A Survey of Historical Learning: Learning Models with Learning History](https://mlsanity.com/paper/2303.12992/) (2023)
- [Probabilistic Test-Time Generalization by Variational Neighbor-Labeling](https://mlsanity.com/paper/2307.04033/) (2023)
- [Few Clicks Suffice: Active Test-Time Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2312.01835/) (2023)
- [Black-box Source-free Domain Adaptation via Two-stage Knowledge Distillation](https://mlsanity.com/paper/2305.07881/) (2023)
- [Enhancing Plasticity for First Session Adaptation Continual Learning](https://mlsanity.com/paper/2310.11482/) (2023)
- [Improving Entropy-Based Test-Time Adaptation from a Clustering View](https://mlsanity.com/paper/2310.20327/) (2023)
- [Exploring Human-in-the-Loop Test-Time Adaptation by Synergizing Active Learning and Model Selection](https://mlsanity.com/paper/2405.18911/) (2024)
- [Optimal Transport for Brain-Image Alignment: Unveiling Redundancy and Synergy in Neural Information Processing](https://mlsanity.com/paper/2503.10663/) (2025)
- [PAID: Pairwise Angular-Invariant Decomposition for Continual Test-Time Adaptation](https://mlsanity.com/paper/2506.02453/) (2025)
- [Test-Time Adaptation by Causal Trimming](https://mlsanity.com/paper/2510.11133/) (2025)
- [Dance Across Shifts: Forward-Facilitation Continual Test-Time Adaptation through Dynamic Style Bridging](https://mlsanity.com/paper/2605.18608/) (2026)

## Abstract (arXiv)

Test time adaptation (TTA) aims to adapt deep neural networks when receiving out of distribution test domain samples. In this setting, the model can only access online unlabeled test samples and pre-trained models on the training domains. We first address TTA as a feature revision problem due to the domain gap between source domains and target domains. After that, we follow the two measurements alignment and uniformity to discuss the test time feature revision. For test time feature uniformity, we propose a test time self-distillation strategy to guarantee the consistency of uniformity between representations of the current batch and all the previous batches. For test time feature alignment, we propose a memorized spatial local clustering strategy to align the representations among the neighborhood samples for the upcoming batch. To deal with the common noisy label problem, we propound the entropy and consistency filters to select and drop the possible noisy labels. To prove the scalability and efficacy of our method, we conduct experiments on four domain generalization benchmarks and four medical image segmentation tasks with various backbones. Experiment results show that our method not only improves baseline stably but also outperforms existing state-of-the-art test time adaptation methods. Code is available at hrefhttps://github.com/SakurajimaMaiii/TSDhttps://github.com/SakurajimaMaiii/TSD.